Imagen de Portada

Sockpuppetting: Jailbreaking LLMs by Combining Prefilling with Optimization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Dotsinski, Asen, Eustratiadis, Panagiotis
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language Cryptography and Security Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs
por: Li, Ran, et al.
Publicado: (2025)

Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
por: Jia, Xiaojun, et al.
Publicado: (2024)

JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs
por: Chu, Junjie, et al.
Publicado: (2024)

Jailbreaking LLMs via Calibration
por: Lu, Yuxuan, et al.
Publicado: (2026)

A StrongREJECT for Empty Jailbreaks
por: Souly, Alexandra, et al.
Publicado: (2024)

Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
por: Mehrotra, Anay, et al.
Publicado: (2023)

Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
por: Struppek, Lukas, et al.
Publicado: (2026)

Sparse Autoencoders are Capable LLM Jailbreak Mitigators
por: Assogba, Yannick, et al.
Publicado: (2026)

Testing the Limits of Jailbreaking Defenses with the Purple Problem
por: Kim, Taeyoun, et al.
Publicado: (2024)

Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs
por: Rando, Javier, et al.
Publicado: (2024)

VERA: Variational Inference Framework for Jailbreaking Large Language Models
por: Lochab, Anamika, et al.
Publicado: (2025)

Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation
por: Li, Qizhang, et al.
Publicado: (2024)

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
por: Zeng, Yifan, et al.
Publicado: (2024)

Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks
por: Hu, Hanjiang, et al.
Publicado: (2025)

KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs
por: Liang, Buyun, et al.
Publicado: (2025)

Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning
por: Hasan, Adib, et al.
Publicado: (2024)

Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement
por: Kim, Heegyu, et al.
Publicado: (2024)

LLMs can be Dangerous Reasoners: Analyzing-based Jailbreak Attack on Large Language Models
por: Lin, Shi, et al.
Publicado: (2024)

From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks
por: Zhang, Zhexin, et al.
Publicado: (2024)

RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking
por: Jiang, Yifan, et al.
Publicado: (2024)

Jailbreak-Zero: A Path to Pareto Optimal Red Teaming for Large Language Models
por: Hu, Kai, et al.
Publicado: (2025)

Jailbreaking in the Haystack
por: Shah, Rishi Rajesh, et al.
Publicado: (2025)

PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling
por: Ma, Avery, et al.
Publicado: (2025)

Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities
por: Geng, Jiahui, et al.
Publicado: (2025)

PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flips
por: Coalson, Zachary, et al.
Publicado: (2024)

TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning
por: Sun, Bowen, et al.
Publicado: (2026)

Red Teaming GPT-4V: Are GPT-4V Safe Against Uni/Multi-Modal Jailbreak Attacks?
por: Chen, Shuo, et al.
Publicado: (2024)

Jailbreaking with Universal Multi-Prompts
por: Hsu, Yu-Ling, et al.
Publicado: (2025)

Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models
por: Li, Xiao, et al.
Publicado: (2024)

LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet
por: Li, Nathaniel, et al.
Publicado: (2024)

AdvPrefix: An Objective for Nuanced LLM Jailbreaks
por: Zhu, Sicheng, et al.
Publicado: (2024)

Rethinking How to Evaluate Language Model Jailbreak
por: Cai, Hongyu, et al.
Publicado: (2024)

Low-Resource Languages Jailbreak GPT-4
por: Yong, Zheng-Xin, et al.
Publicado: (2023)

Jailbreaking Large Language Models with Symbolic Mathematics
por: Bethany, Emet, et al.
Publicado: (2024)

How Vulnerable Are Edge LLMs?
por: Ding, Ao, et al.
Publicado: (2026)

Universal Jailbreak Backdoors from Poisoned Human Feedback
por: Rando, Javier, et al.
Publicado: (2023)

EnJa: Ensemble Jailbreak on Large Language Models
por: Zhang, Jiahao, et al.
Publicado: (2024)

UCD: Unlearning in LLMs via Contrastive Decoding
por: Suriyakumar, Vinith M., et al.
Publicado: (2025)

Coercing LLMs to do and reveal (almost) anything
por: Geiping, Jonas, et al.
Publicado: (2024)

The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation
por: Xiong, Alexander, et al.
Publicado: (2025)